18 citations · 44 across the 16 of their papers we have counts for
12 papers · 1 filter
Anchored Spectral Estimator for Rigid Motion Synchronization
Ziyue Zhao, Huikang Liu, Man-Chung Yue
A rigid motion in consists of a proper rotation and a translation, and it can be represented as a matrix in . The problem of rigid mo…
On the Estimation Performance of Generalized Power Method for Heteroscedastic Probabilistic PCA
Jinxin Wang, Chonghe Jiang, Huikang Liu +1
The heteroscedastic probabilistic principal component analysis (PCA) technique, a variant of the classic PCA that considers data heterogeneity, is receiving more and more attention…
ReSync: Riemannian Subgradient-based Robust Rotation Synchronization
Huikang Liu, Xiao Li, Anthony Man-Cho So
This work presents ReSync, a Riemannian subgradient-based algorithm for solving the robust rotation synchronization problem, which arises in various engineering applications. ReSyn…
A Communication-Efficient Decentralized Newton's Method with Provably Faster Convergence
Huikang Liu, Jiaojiao Zhang, Anthony Man-Cho So +1
In this paper, we consider a strongly convex finite-sum minimization problem over a decentralized network and propose a communication-efficient decentralized Newton's method for so…
Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering
Peng Wang, Huikang Liu, Anthony Man-Cho So +1
The K-subspaces (KSS) method is a generalization of the K-means method for subspace clustering. In this work, we present local convergence analysis and a recovery guarantee for KSS…
Variance-Reduced Stochastic Quasi-Newton Methods for Decentralized Learning: Part II
Jiaojiao Zhang, Huikang Liu, Anthony Man-Cho So +1
In Part I of this work, we have proposed a general framework of decentralized stochastic quasi-Newton methods, which converge linearly to the optimal solution under the assumption…
Variance-Reduced Stochastic Quasi-Newton Methods for Decentralized Learning: Part I
Jiaojiao Zhang, Huikang Liu, Anthony Man-Cho So +1
In this work, we investigate stochastic quasi-Newton methods for minimizing a finite sum of cost functions over a decentralized network. In Part I, we develop a general algorithmic…
Linear Convergence of a Proximal Alternating Minimization Method with Extrapolation for -Norm Principal Component Analysis
Peng Wang, Huikang Liu, Anthony Man-Cho So
A popular robust alternative of the classic principal component analysis (PCA) is the -norm PCA (L1-PCA), which aims to find a subspace that captures the most variation in…
Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method
Peng Wang, Huikang Liu, Zirui Zhou +1
In this paper, we study the problem of exact community recovery in the symmetric stochastic block model, where a graph of vertices is randomly generated by partitioning the ver…
A Unified Approach to Synchronization Problems over Subgroups of the Orthogonal Group
Huikang Liu, Man-Chung Yue, Anthony Man-Cho So
The problem of synchronization over a group aims to estimate a collection of group elements based on noisy observations of a sub…
On the Estimation Performance and Convergence Rate of the Generalized Power Method for Phase Synchronization
Huikang Liu, Man-Chung Yue, Anthony Man-Cho So
An estimation problem of fundamental interest is that of phase synchronization, in which the goal is to recover a collection of phases using noisy measurements of relative phases.…
Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods
Huikang Liu, Weijie Wu, Anthony Man-Cho So
A fundamental class of matrix optimization problems that arise in many areas of science and engineering is that of quadratic optimization with orthogonality constraints. Such probl…